“Xingchao work”版本间的差异
来自cslt Wiki
（→=Simple semi-linear autoencoder） |
（→Reproduce Nested Dropout） |
||
| 第3行： | 第3行： | ||
===Reproduce Nested Dropout=== | ===Reproduce Nested Dropout=== | ||
Nested dropout method proposed by Rippel et. in their paper "Learning Ordered Representations with Nested Dropout", they proposed a dropout method which could learning ordered information in different dimensions. | Nested dropout method proposed by Rippel et. in their paper "Learning Ordered Representations with Nested Dropout", they proposed a dropout method which could learning ordered information in different dimensions. | ||
| + | |||
====Simple semi-linear autoencoder==== | ====Simple semi-linear autoencoder==== | ||
Their first draft work is semi-linear autoencoder, so I will reproduce this work. | Their first draft work is semi-linear autoencoder, so I will reproduce this work. | ||
2015年7月2日 (四) 11:25的版本
目录
Chaos Work
Binary Word Vector
Reproduce Nested Dropout
Nested dropout method proposed by Rippel et. in their paper "Learning Ordered Representations with Nested Dropout", they proposed a dropout method which could learning ordered information in different dimensions.
Simple semi-linear autoencoder
Their first draft work is semi-linear autoencoder, so I will reproduce this work.
And I will compare this work to PCA.
We only consider one hidden layer.
Start at 2015-07-02 20:00
